© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1955
    Prev
    Next
    INDEX
    Explanations

    words related to education, activities, and organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    437
    +0.17
    0.6%
    167
    +0.16
    0.5%
    356
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.07
    683
    +0.16
    0.05
    232
    +0.15
    0.04
    Negative Logits
    PER
    -1.28
    pheus
    -1.19
    ĸļ
    -1.16
    ĺħ
    -1.05
    uyomi
    -1.04
    igslist
    -1.03
    psons
    -1.02
    phis
    -0.98
    raltar
    -0.97
     Pastebin
    -0.94
    POSITIVE LOGITS
    ice
    1.25
    ragon
    1.23
    rums
    1.21
    ard
    1.20
    furt
    1.19
    robe
    1.18
    hart
    1.12
    aign
    1.11
    fman
    1.09
    stown
    1.09
    Activations Density 1.419%

    No Known Activations